DeepSeek R1 (Jan '25) vs Qwen3.8 27B (Medium)
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or Qwen3.8 27B (Medium) by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
Qwen3.8 27B (Medium) scores 16.2 points higher (27.6 vs 11.4) but costs 2.5× as much to run the benchmark ($1165 vs $461; premium vs mid-range cost classes). Pick Qwen3.8 27B (Medium) when the extra intelligence is worth the premium, otherwise DeepSeek R1 (Jan '25).
| Metric | DeepSeek R1 (Jan '25) | Qwen3.8 27B (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 27.6 | +142.1% Qwen3.8 27B (Medium) is 2.4× more intelligent |
| Total AA cost (lower is better) | $460.74 | $1,165.00 | +152.9% Qwen3.8 27B (Medium) is 2.5× more expensive |
| End-to-end time (lower is better) | 19.17s | 56.45s | +194.5% Qwen3.8 27B (Medium) is 194.5% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $0.50 / $3.00 | |
| Input modalities | Text | Text, Image, Video |
Qwen3.8 27B (Medium) vs DeepSeek R1 (Jan '25): 142.1% more intelligence, 152.9% more cost to run the AA benchmark, and 194.5% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek R1 (Jan '25) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- Qwen3.8 27B (Medium) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
DeepSeek R1 (Jan '25)Qwen3.8 27B (Medium)Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-r1-0120/qwen3-8-27b-medium · Markdown: /api/v1/compare/deepseek-r1-0120/qwen3-8-27b-medium?format=md · llms.txt · agent skill